Show simple item record

dc.contributor.authorCarreras Pérez, Xavier
dc.contributor.authorCollins, Michael
dc.identifier.citationCarreras, X.; Collins, M. Non-projective parsing for statistical machine translation. A: Conference on Empirical Methods in Natural Language Processing. "Conference on Empirical Methods in Natural Language Processing 2009". Singapur: 2009, p. 200-209.
dc.description.abstractWe describe a novel approach for syntaxbased statistical MT, which builds on a variant of tree adjoining grammar (TAG). Inspired by work in discriminative dependency parsing, the key idea in our approach is to allow highly flexible reordering operations during parsing, in combination with a discriminative model that can condition on rich features of the sourcelanguage string. Experiments on translation from German to English show improvements over phrase-based systems, both in terms of BLEU scores and in human evaluations.
dc.format.extent10 p.
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural
dc.subject.lcshComputational linguistics
dc.titleNon-projective parsing for statistical machine translation
dc.typeConference report
dc.subject.lemacLingüística computacional
dc.contributor.groupUniversitat Politècnica de Catalunya. GPLN - Grup de Processament del Llenguatge Natural
dc.description.peerreviewedPeer Reviewed
dc.rights.accessOpen Access
dc.description.versionPostprint (author’s final draft)
local.citation.authorCarreras, X.; Collins, M.
local.citation.contributorConference on Empirical Methods in Natural Language Processing
local.citation.publicationNameConference on Empirical Methods in Natural Language Processing 2009

Files in this item


This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder